(Online): 2347-1697

Research Paper
Volume 2
Issue 4
December 2014
International Journal of Informative & Futuristic Research
ISSN (Online): 2347-1697
A System for Filtering of Text and Image
Messages on OSN User Space
Paper ID
Key Words
IJIFR/ V2/ E4/ 003
Page No.
851-858
Subject Area
Computer Engineering
OSN, Machine Learning, Privacy, Radial Basis Function Networks
Shejwal Shalini K.
Prof. N. G. Pardeshi
Prof. A. O. Rathi
M.E. Scholar, Department of Computer Engineering ,
Sanjivani Rural Education Society College of Engineering,
Kopargaon (Maharashtra)
Professor, Department of Computer Engineering ,
Sanjivani Rural Education Society College of Engineering,
Kopargaon (Maharashtra)
Department of Computer Engineering
Sir Visvesvaraya Institute Of Technology
Chincholi,Nashik(Maharashtra)
Abstract
Internet becomes more popular in the day to day activities of users. In recent
years online social networks (OSN) also increased rapidly. The users can
communicate and share their views and content through online social
networking services (OSN). The sharing between the users should be several
types of content like image, audio, video etc. The main draw-back of these
Online Social Networking (OSN) services is the lack of privacy for the users
own private space. The users can’t have the ability to direct control to
prevent the undesired messages posted on their own private walls. Online
Social Networks (OSN) becomes an important part of many people life today.
So Online Social Networks (OSN) should be highly secured to prevent the
individual’s privacy. Up to now the Online Social Network (OSN) provides
the security measures are limited. To filter the unwanted messages, in this
work proposed an enhanced filtering system by using machine learning
technique based on a content filtering.
1. Introduction
The aim of the present work is therefore to propose and experimentally evaluate an automated
system, called Filtered Wall (FW), able to filter unwanted messages from OSN user walls. We exploit
Machine Learning (ML) text categorization techniques to automatically assign with each short text
message a set of categories based on its content. The major efforts in building a robust short text
www.ijifr.com
Copyright © IJIFR 2014
851
ISSN (Online): 2347-1697
International Journal of Informative & Futuristic Research (IJIFR)
Volume - 2, Issue - 4, December 2014
16th Edition, Page No: 851-858
classifier are concentrated in the extraction and selection of a set of characterizing and discriminate
features. The solutions investigated in this paper are an extension of those adopted in a previous work
by us from whom we inherit the learning model and the elicitation procedure for generating preclassified data. The original set of features, derived from endogenous properties of short texts, is
enlarged here including exogenous knowledge related to the context from which the messages
originate. The role of interface design is to reconcile the differences that prevail among the software
engineers design model. The designed system meets the end user requirement with economical way at
minimal cost within the affordable price by encouraging more of proposed system. Economic
feasibility is concerned with comparing the development cost with the income/benefit derived from
the developed system.
In this we need to derive how this project will help the management to take effective
decisions. As far as the learning model is concerned, we confirm in the current paper the use of neural
learning which is today recognized as one of the most efficient solutions in text classification. In
particular, we base the overall short text classification strategy on Radial Basis Function Networks
(RBFN) for their proven capabilities in acting as soft classifiers, in managing noisy data and
intrinsically vague classes. The architecture of OSN services is a three-tier structure of three layers.
These three layers are:
Figure 1.1: Filtered wall architecture.
• Social Network Manager (SNM)
The main task of Social network management layer is profile and relationship management. It
maintains the data related to user profile and provides the data to the second layer for applying
filtering rules (FR) and blacklists (BL).
• Social Network Application (SNA)
Second layer composed of Content Base Message Filtering (CBMF) and a short text classifier is most
important layer. The classifier categorizes each message according to its content and CBMF filters
the message according to filtering criteria and blacklist provided by the user.
Shejwal Shalini K. , Prof. N. G. Pardeshi , Prof. A. O. Rathi : A System for
Filtering of Text and Image Messages on OSN User Space.
852
ISSN (Online): 2347-1697
International Journal of Informative & Futuristic Research (IJIFR)
Volume - 2, Issue - 4, December 2014
16th Edition, Page No: 851-858
• Graphical User Interface (GUI)
Third layer consist of graphical user interface by which user provide his input and is able to see
published wall messages.
1. After entering the private wall of one of his/her contacts, the user tries to post a message, which is
intercepted by FW.
2. A ML-based text classifier extracts metadata from the content of the message.
3. FW uses metadata provided by the classifier, together with data extracted from the social graph and
users profiles, to enforce the filtering and BL rules. Depending on the result of the previous step, the
message will be published or filtered by FW.
2 Scope And Objective
Scope:
• Online Social Networks enables its users to keep in touch with friends by exchanging several type
of content including text, audio and video data.
• To control the messages posted on their own private space to avoid that unwanted content is
displayed.
Objectives:
• To design an online message filtering system that is deployed at the OSN service provider side.
• To considered the challenges in short text classification and filtering criteria while publishing
messages on user wall.
• Once deployed, To inspects every message before rendering the message to the intended recipients
and makes immediate decision on whether or not the message under inspection should be dropped.
Figure 2.1 : Structure of System
Shejwal Shalini K. , Prof. N. G. Pardeshi , Prof. A. O. Rathi : A System for
Filtering of Text and Image Messages on OSN User Space.
853
ISSN (Online): 2347-1697
International Journal of Informative & Futuristic Research (IJIFR)
Volume - 2, Issue - 4, December 2014
16th Edition, Page No: 851-858
3 Class of Problem
The Class P
P is the class of decisions that are polynomials bounded. P is defined only for decision problems. It
may seem rather extravagant to use the existence of a polynomial time bound as the criterion for
defining the class of more or less reasonable problems polynomials can be quite large. There are,
however a number of good reasons for this choice. First, while it is not true that every problem in P
has an acceptably efficient algorithm, we can certainly say that if a problem is not in P, it will be
extremely expensive and probably impossible to solve in practice. A second reason for using a
polynomial bound to define p is that polynomials have nice ”closure” properties. An algorithm for a
complex problem may be obtained by combining several algorithms for simpler problems. Some of
the simpler algorithms may work on the output or intermediate result of others. A third reason for a
using polynomial bound is that it makes P independent of the particular formal model of computation
used. A number of formal models are used to prove rigorous theorems about the complexity of
algorithms and problems.
The Class NP
NP is the class of decision problems for which a given proposed solution for a given input can be
checked quickly (in polynomial time) to see if it really is a solution. More formally, inputs for a
system and proposed solution must be described by strings of symbols from some finite set.
There may be decision problems where there is no natural interpretation for ”solutions” and
”proposed solutions”. A decision problem is abstractly just some function from a set of input string to
the set yes, no. A formal definition of NP considers all decision problems.
NP-Hard Problems
NP-hard (Non-Deterministic polynomial time hard), in computational complexity theory, is a class of
problems that are, informally at least as hard as the hardest problem in NP.
A problem H is NP-hard if and only if there is an NP-complete L that is polynomial time turing
reducible to H.
NP-hard problems may be of any type: Decision problems, search problems or optimization
problems.
NP-Complete Problems
NP-Complete is the term used to describe decision problems that are the hardest ones in NP in the
sense that, if there were a polynomials bounded algorithm for an NP-complete problem, then there
would be a polynomials bounded algorithm for each problem in NP. This is a P class problem. The
algorithms used in this system are fixed Algorithms. So it will not go into NP Hard class.
4 Modules

Login

Friend Request

Filtering rules

Online setup assistant for FRs thresholds(Classifiers)

Blacklists
Module 1: Login and Registration Module:
In this module, user can register their details like name, password, gender, age, and then. Here the
user can make friends by accept friend request
or send friend request. They can share their status by messages also share
Shejwal Shalini K. , Prof. N. G. Pardeshi , Prof. A. O. Rathi : A System for
Filtering of Text and Image Messages on OSN User Space.
854
ISSN (Online): 2347-1697
International Journal of Informative & Futuristic Research (IJIFR)
Volume - 2, Issue - 4, December 2014
16th Edition, Page No: 851-858
videos with friends and get comments from them.
Module 2: Friend Request:
Search Friends: Here they can search for a friends and send a request
to them also can view their details.
Accept Request: In this Module, Accept the friend request along with category.
Share Comments: They can share videos with his friends by adding comments they share their status
by sending messages to friends.
Implementation Steps (Algorithm/Code)
1:Login and Registration
Steps:
1. User is connected to facebook(OSN system)
2. take Input as a username and password from user.
3. If user enter correct username and password then login successfully Otherwise re-entered.
4. Once user connected to Facebook, user gives input to module2(Friend request)
Figure 4.1: Login & Authentication Friend Request
Shejwal Shalini K. , Prof. N. G. Pardeshi , Prof. A. O. Rathi : A System for
Filtering of Text and Image Messages on OSN User Space.
855
ISSN (Online): 2347-1697
International Journal of Informative & Futuristic Research (IJIFR)
Volume - 2, Issue - 4, December 2014
16th Edition, Page No: 851-858
5 Design Goals
Here in this section we characterize certain design goals that are taken as pre requisites for designing
the proposed work. These include aspects relating to access, privacy, storage and efficiency.
ACCESS:
Admin must register himself before his login for obtain the details of the user. Once he register admin
can view user's profile, how many bad words a message contains and whenever admin filters any
message then a pop up window is appeared to that particular user whose message is filtered.
PRIVACY:
Whenever any user updates his status or his profile image immediately he will logout of his account
and he want to login again to view his status or image.it gives more security to the user.
STORAGE:
In the system we have many number of admins and users so the system provides a database which
stores all these details. When admin logins he can directly access the users databases.
EFFICIENCY:
The efficiency of the proposed scheme works as follows: as we can have more number of admins the
later performance will be high. The proposed work is based on the content -based altering which is in
advance of the existing system.
Figure 5.1: Filtering Process
Module 4:
Online setup assistant for FRs thresholds (Classifiers) As mentioned in the previous section, we
address the problem of setting thresholds to filter rules, by conceiving and implementing within FW,
an Online Setup Assistant (OSA) procedure. OSA presents the user with a set of messages selected
from the dataset. For each message, the user tells the system the decision to accept or reject the
message. The collection and processing of user decisions on an adequate set of messages distributed
Shejwal Shalini K. , Prof. N. G. Pardeshi , Prof. A. O. Rathi : A System for
Filtering of Text and Image Messages on OSN User Space.
856
ISSN (Online): 2347-1697
International Journal of Informative & Futuristic Research (IJIFR)
Volume - 2, Issue - 4, December 2014
16th Edition, Page No: 851-858
over all the classes allows to compute customized threshresholds representing the user attitude in
accepting or rejecting certain contents. Such messages are selected according to the following
process. A certain amount of non- neutral messages taken from a fraction of the dataset and not
belonging to the training/test sets, are classified by the ML in order to have, for each message, the
second level class membership values.
Module 5: Blacklists:
A further component of our system is a BL mechanism to avoid messages from undesired creators,
independent from their contents. BLs are directly managed by the system, which should be able to
determine who are the users to be inserted in the BL and decide when users retention in the BL is
finished. To enhance edibility, such information are given to the system through a set of rules,
hereafter called BL rules. Such rules are not define by the SNM, therefore they are not meant as
general high level directives to be applied to the whole community.
Figure 5.2: Blacklist Process
6 Testing & Result (Analysis)
Table 6.1 : Result Analysis
Sr.no Msg send on Login
& Friend
facebook
Registration Request
(OSN Wall)
Module
Module
1.
User Login Yes
successfully
No
Filtering Classification Blacklist Msg
Module Module
Post on
User
Wall
No
No
No
No
Shejwal Shalini K. , Prof. N. G. Pardeshi , Prof. A. O. Rathi : A System for
Filtering of Text and Image Messages on OSN User Space.
857
ISSN (Online): 2347-1697
International Journal of Informative & Futuristic Research (IJIFR)
Volume - 2, Issue - 4, December 2014
16th Edition, Page No: 851-858
2.
3.
to facebook
(OSN)
User
send Yes
Friend
request on
facebook
User share Yes
msg
on
facebbok
Yes
No
No
No
No
Yes
No
No
No
Yes
7 Conclusion & Future Scope:
The System work to provide unwanted message filtering for social networks. we have presented a
system to filter undesired messages from OSN walls. The system exploits a ML soft classifier to
enforce customizable content-dependent FRs. Moreover, the flexibility of the system in terms of
filtering options is enhanced through the management of BLs. Proposed system represents just the
core set of functionalities needed to provide a sophisticated tool for OSN message filtering.
Additionally, strategies and techniques limiting the inferences that a user can do on the enforced
filtering rules with the aim of bypassing the filtering system, such as for instance randomly notifying
a message that should instead be blocked, or detecting modifications to profile attributes that have
been made for the only purpose of defeating the filtering system.
Future scope of this system is that Video Filtering Techniques. In proposed system, only filter the text
and Image messages. So video filtering will be tried in my future system.
References
[1] Marco Vanetti, Elisabetta Binaghi, Elena Ferrari, Barbara Carminati, Moreno Carullo, "A System to Filter
Unwanted Messages from OSN User Walls, " IEEE Transaction on Knowledge and Data Engineering,vol. 25,
2013.
[2] P. E. Baclace, "Competitive agents for information _ltering, " Communications of the ACM, vol. 35, no. 12,
p. 50, 1992.
[3] R.J.Mooney and L.Roy, "Content-Based Book Recommending UsingLearning for Text Categorization,"
2000.
[4] K. Nirmala, S. Satheesh kumar, "A Survey on Text Categorization in Online Social Networks" in
Proceedings of International Journal of Emerging Technology and Advanced Engineering,Volume 3, Issue 9,
September 2013.
[5] V.Bobicev and M.Sokolova, "An E_ective and Robust Method for Short Text Classi_cation," Proc.23rd Nat'l
Conf. Arti_cial Intelligence (AAAI), D.Fox and C.P.Gomes, eds., pp.1444-1445,2008.
[6] J.Colbeck, "Combining Provenance with Trust in Social Networks for Semantic Web Content Filtering,"
Proc. Int'l conf. Provenance and Annotation of Data, L.Moreau and I.Foster, eds. M. Vanetti, E. Binaghi, B.
Carminati, M. Carullo, and E. Ferrari, "Content-based
_ltering in on-line social networks , "in Proceedings of ECML/PKDD Workshop on Privacy and Security issues
in Data Mining and Machine Learning.
[7] M.Carullo, E.Binaghi, and I. Gallo, "An Online Document Clustering Technique for short Web contents,"
Pattern Recognition Letters,vol.30, pp.870-876, July 2009.
[8] Buktar Umakant D.” An execution of Intrusion detection system by using genetic algorithm” IJIFR volume
1,Issue 10, Paper ID: IJIFR/V1/E10/006, pp14-19, ,June 2014
Shejwal Shalini K. , Prof. N. G. Pardeshi , Prof. A. O. Rathi : A System for
Filtering of Text and Image Messages on OSN User Space.
858

Download Report